Zoyd commited on
Commit
5e5d0ec
1 Parent(s): d83d02b

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model:
5
+ - microsoft/Phi-3-medium-128k-instruct
6
+ datasets:
7
+ - flammenai/FlameMix-DPO-v1
8
+ - flammenai/Grill-preprod-v1_chatML
9
+ - flammenai/Grill-preprod-v2_chatML
10
+ ---
11
+ ![image/png](https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png)
12
+
13
+ # Mahou-1.2-phi-14B
14
+
15
+ Please note: this is an untested, experimental release.
16
+
17
+ Mahou is our attempt to build a production-ready conversational/roleplay LLM.
18
+
19
+ Future versions will be released iteratively and finetuned from flammen.ai conversational data.
20
+
21
+ ### Chat Format
22
+
23
+ This model has been trained to use ChatML format.
24
+
25
+ ```
26
+ <|im_start|>system
27
+ {{system}}<|im_end|>
28
+ <|im_start|>{{char}}
29
+ {{message}}<|im_end|>
30
+ <|im_start|>{{user}}
31
+ {{message}}<|im_end|>
32
+ ```
33
+
34
+ # Roleplay Format
35
+
36
+ - Speech without quotes.
37
+ - Actions in `*asterisks*`
38
+
39
+ ```
40
+ *leans against wall cooly* so like, i just casted a super strong spell at magician academy today, not gonna lie, felt badass.
41
+ ```
42
+
43
+ ### ST Settings
44
+
45
+ 1. Use ChatML for the Context Template.
46
+ 2. Turn on Instruct Mode for ChatML.
47
+ 3. Use the following stopping strings: `["<", "|", "<|", "\n"]`
48
+
49
+ ### Method
50
+
51
+ Finetuned using an A100 on Google Colab.
52
+
53
+ [Fine-tune a Mistral-7b model with Direct Preference Optimization](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) - [Maxime Labonne](https://huggingface.co/mlabonne)
54
+
55
+ ### Configuration
56
+
57
+ LoRA, model, and training settings:
58
+
59
+ ```python
60
+ # LoRA configuration
61
+ peft_config = LoraConfig(
62
+ r=16,
63
+ lora_alpha=16,
64
+ lora_dropout=0.05,
65
+ bias="none",
66
+ task_type="CAUSAL_LM",
67
+ target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
68
+ )
69
+
70
+ # Model to fine-tune
71
+ model = AutoModelForCausalLM.from_pretrained(
72
+ model_name,
73
+ torch_dtype=torch.bfloat16,
74
+ load_in_4bit=True
75
+ )
76
+ model.config.use_cache = False
77
+
78
+ # Reference model
79
+ ref_model = AutoModelForCausalLM.from_pretrained(
80
+ model_name,
81
+ torch_dtype=torch.bfloat16,
82
+ load_in_4bit=True
83
+ )
84
+
85
+ # Training arguments
86
+ training_args = TrainingArguments(
87
+ per_device_train_batch_size=4,
88
+ gradient_accumulation_steps=4,
89
+ gradient_checkpointing=True,
90
+ learning_rate=5e-5,
91
+ lr_scheduler_type="cosine",
92
+ max_steps=2000,
93
+ save_strategy="no",
94
+ logging_steps=1,
95
+ output_dir=new_model,
96
+ optim="paged_adamw_32bit",
97
+ warmup_steps=100,
98
+ bf16=True,
99
+ report_to="wandb",
100
+ )
101
+
102
+ # Create DPO trainer
103
+ dpo_trainer = DPOTrainer(
104
+ model,
105
+ ref_model,
106
+ args=training_args,
107
+ train_dataset=dataset,
108
+ tokenizer=tokenizer,
109
+ peft_config=peft_config,
110
+ beta=0.1,
111
+ force_use_ref_model=True
112
+ )
113
+
114
+ # Fine-tune model with DPO
115
+ dpo_trainer.train()
116
+ ```
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3-medium-128k-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-3-medium-128k-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3-medium-128k-instruct--modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 32000,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 5120,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 17920,
19
+ "max_position_embeddings": 131072,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 40,
22
+ "num_hidden_layers": 40,
23
+ "num_key_value_heads": 10,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": null,
26
+ "resid_pdrop": 0.0,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": {
29
+ "long_factor": [
30
+ 1.0,
31
+ 1.0,
32
+ 1.0,
33
+ 1.0,
34
+ 1.0,
35
+ 1.0,
36
+ 1.0,
37
+ 1.0,
38
+ 1.0,
39
+ 1.0,
40
+ 1.0,
41
+ 1.0,
42
+ 1.0,
43
+ 1.25,
44
+ 1.25,
45
+ 1.5,
46
+ 2.0,
47
+ 2.75,
48
+ 5.75,
49
+ 5.75,
50
+ 6.5,
51
+ 9.25,
52
+ 11.0,
53
+ 13.25,
54
+ 19.25,
55
+ 19.75,
56
+ 19.75,
57
+ 21.25,
58
+ 21.5,
59
+ 26.5,
60
+ 30.0,
61
+ 33.75,
62
+ 35.25,
63
+ 38.5,
64
+ 42.0,
65
+ 42.25,
66
+ 46.0,
67
+ 47.0,
68
+ 50.0,
69
+ 50.5,
70
+ 51.0,
71
+ 52.0,
72
+ 52.75,
73
+ 53.75,
74
+ 54.75,
75
+ 57.0,
76
+ 57.25,
77
+ 58.5,
78
+ 59.25,
79
+ 59.5,
80
+ 62.0,
81
+ 62.5,
82
+ 62.75,
83
+ 63.25,
84
+ 63.25,
85
+ 63.25,
86
+ 63.75,
87
+ 64.0,
88
+ 64.0,
89
+ 64.25,
90
+ 64.5,
91
+ 64.5,
92
+ 65.0,
93
+ 65.0
94
+ ],
95
+ "short_factor": [
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.0,
102
+ 1.01,
103
+ 1.02,
104
+ 1.02,
105
+ 1.04,
106
+ 1.04,
107
+ 1.07,
108
+ 1.07,
109
+ 1.1,
110
+ 1.3000000000000003,
111
+ 1.3000000000000003,
112
+ 1.5000000000000004,
113
+ 1.5700000000000005,
114
+ 1.9000000000000008,
115
+ 2.3100000000000014,
116
+ 2.759999999999992,
117
+ 3.3899999999999784,
118
+ 3.9399999999999666,
119
+ 4.009999999999965,
120
+ 4.289999999999959,
121
+ 4.349999999999958,
122
+ 5.349999999999937,
123
+ 6.659999999999909,
124
+ 7.029999999999901,
125
+ 7.51999999999989,
126
+ 8.00999999999988,
127
+ 8.249999999999876,
128
+ 8.279999999999875,
129
+ 9.629999999999846,
130
+ 9.89999999999984,
131
+ 10.589999999999826,
132
+ 11.049999999999816,
133
+ 11.7899999999998,
134
+ 12.189999999999792,
135
+ 12.889999999999777,
136
+ 13.129999999999772,
137
+ 13.16999999999977,
138
+ 13.20999999999977,
139
+ 13.479999999999764,
140
+ 13.539999999999763,
141
+ 13.779999999999758,
142
+ 13.929999999999755,
143
+ 14.429999999999744,
144
+ 14.759999999999737,
145
+ 15.149999999999729,
146
+ 15.419999999999723,
147
+ 15.53999999999972,
148
+ 15.659999999999718,
149
+ 15.749999999999716,
150
+ 15.759999999999716,
151
+ 15.799999999999715,
152
+ 16.05999999999971,
153
+ 16.079999999999714,
154
+ 16.11999999999972,
155
+ 16.11999999999972,
156
+ 16.18999999999973,
157
+ 16.31999999999975,
158
+ 16.539999999999786,
159
+ 16.799999999999827
160
+ ],
161
+ "type": "su"
162
+ },
163
+ "rope_theta": 10000.0,
164
+ "sliding_window": 131072,
165
+ "tie_word_embeddings": false,
166
+ "torch_dtype": "bfloat16",
167
+ "transformers_version": "4.41.0",
168
+ "use_cache": true,
169
+ "vocab_size": 32064,
170
+ "quantization_config": {
171
+ "quant_method": "exl2",
172
+ "version": "0.0.21",
173
+ "bits": 5.0,
174
+ "head_bits": 6,
175
+ "calibration": {
176
+ "rows": 100,
177
+ "length": 2048,
178
+ "dataset": "(default)"
179
+ }
180
+ }
181
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.41.0"
11
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 27920476160
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
21
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
22
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
23
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
24
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
25
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
26
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
27
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
28
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
81
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
82
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
83
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
84
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
85
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
86
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
93
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
95
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
96
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
106
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
107
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
109
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
117
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
118
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
119
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
120
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
121
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
122
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
123
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
124
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
125
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
127
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
128
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
129
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
130
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
135
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
136
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
137
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
138
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
141
+ "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
142
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
143
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
144
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
145
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
146
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
147
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
148
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
149
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
150
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
151
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
152
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
153
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
154
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
158
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
159
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
160
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
161
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
163
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
164
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
165
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.32.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.32.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
170
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
171
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
172
+ "model.layers.33.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
173
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
174
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
175
+ "model.layers.33.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
176
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
177
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
178
+ "model.layers.34.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
179
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
180
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
181
+ "model.layers.34.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
182
+ "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
183
+ "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
184
+ "model.layers.35.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
185
+ "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
186
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
187
+ "model.layers.35.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
189
+ "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
190
+ "model.layers.36.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
191
+ "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
192
+ "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
193
+ "model.layers.36.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
194
+ "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
195
+ "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
196
+ "model.layers.37.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
197
+ "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
198
+ "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
199
+ "model.layers.37.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
200
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
201
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
202
+ "model.layers.38.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
203
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
204
+ "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
205
+ "model.layers.38.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
206
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
207
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
208
+ "model.layers.39.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
209
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
210
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
211
+ "model.layers.39.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
212
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
213
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
214
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
215
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
217
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
226
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
228
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
229
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
230
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
231
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
232
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
233
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
234
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
235
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
236
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
237
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
238
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
239
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
240
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
241
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
242
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
243
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
244
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
245
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
246
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
247
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
248
+ "model.norm.weight": "model-00006-of-00006.safetensors"
249
+ }
250
+ }
output-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c116330d7cfe7b4eeb5f571c202258d1b877684f896862a2198bba81579bcb
3
+ size 8567386098
output-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f89d25a8cd2c512a544437d8c11b5dc70c7b2f112c06da4f59655b894289a50c
3
+ size 407400520
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ }
117
+ },
118
+ "bos_token": "<s>",
119
+ "chat_template": "{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "model_max_length": 131072,
123
+ "pad_token": "<|endoftext|>",
124
+ "padding_side": "left",
125
+ "sp_model_kwargs": {},
126
+ "tokenizer_class": "LlamaTokenizer",
127
+ "unk_token": "<unk>",
128
+ "use_default_system_prompt": false
129
+ }